Complete Deep Learning In R With Keras & Others

Course Curriculum

Chapter 1: INTRODUCTION TO THE COURSE: The Key Concepts and Software Tools

Lecture 1: Introduction to the Course

Lecture 2: Data and Code

Lecture 3: Install R and RStudio

Lecture 4: Install MXnet in R and RStudio

Lecture 5: Install Mxnet in R- Written Instructions

Lecture 6: Install H2o

Lecture 7: What is Keras?

Lecture 8: Install Keras in R

Lecture 9: What Are the Most Common Data Types We Will Encounter?

Chapter 2: Basic Data Access & Pre-Processing in R

Lecture 1: Read in Data From CSV and Excel Files

Lecture 2: Read in Data from Online HTML Tables-Part 1

Lecture 3: Read in Data from Online HTML Tables-Part 2

Lecture 4: Working with External Data in H2o

Lecture 5: Remove NAs

Lecture 6: More Data Cleaning

Lecture 7: Introduction to dplyr for Data Summarizing-Part 1

Lecture 8: Introduction to dplyr for Data Summarizing-Part 2

Lecture 9: Exploratory Data Analysis(EDA): Basic Visualizations with R

Chapter 3: Some Theoretical Foundations

Lecture 1: Difference Between Supervised & Unsupervised Learning

Lecture 2: Theory Behind ANN (Artificial Neural Network) and DNN (Deep Neural Networks)

Lecture 3: What Are Activation Functions?

Chapter 4: Build Artificial Neural Networks (ANN) in R

Lecture 1: Neural Network for Binary Classifications

Lecture 2: Evaluate Accuracy

Lecture 3: Implement a Multi-Layer Perceptron (MLP) For Supervised Classification

Lecture 4: Neural Network for Multiclass Classifications

Lecture 5: Neural Network for Image Type Data

Lecture 6: Multi-class Classification Using Neural Networks with caret

Lecture 7: Implement an ANN with H2o For Multi-Class Supervised Classification

Lecture 8: Implement an ANN Based Classification Using MXNet

Lecture 9: Implement MLP With Keras

Lecture 10: Keras MLP On Real Data

Lecture 11: Keras MLP For Regression

Lecture 12: Neural Network for Regression

Lecture 13: More on Artificial Neural Networks(ANN) – with neuralnet

Lecture 14: Implement an ANN Based Regression Using MXNet

Lecture 15: Identify Variable Importance in Neural Networks

Chapter 5: Build Deep Neural Networks (DNN) in R

Lecture 1: Implement a Simple DNN With "neuralnet" for Binary Classifications

Lecture 2: Implement a Simple DNN With "deepnet" for Regression

Lecture 3: Implement a DNN with H2o For Multi-Class Supervised Classification

Lecture 4: Implement a (Less Intensive) DNN with H2o For Supervised Classification

Lecture 5: Implement a DNN With Keras

Lecture 6: Identify Variable Importance

Lecture 7: Implement MXNET via "caret"

Lecture 8: Implement a DNN with H2o For Regression

Lecture 9: Implement a DNN with Keras For Regression

Lecture 10: Implement DNN Regression With Keras (Real Data)

Chapter 6: Unsupervised Classification with Deep Learning

Lecture 1: Theory Behind Unsupervised Classification

Lecture 2: Autoencoders for Unsupervised Learning

Lecture 3: Autoencoders for Credit Card Fraud Detection

Lecture 4: Use the Autoencoder Model for Anomaly Detection

Lecture 5: Autoencoders for Unsupervised Classification

Lecture 6: Autoencoders With Keras

Lecture 7: Keras Autoencoders on Real Data

Lecture 8: Stacked Autoencoder With Keras

Lecture 9: Keras For Outlier Detection

Lecture 10: Find the Outlier

Lecture 11: Outlier Detection For Cancer (With Keras)

Chapter 7: Convolutional Neural Networks (CNN)

Lecture 1: What is a CNN?

Lecture 2: Implement a CNN for Multi-Class Supervised Classification

Lecture 3: More About Our CNN Model Accuracy

Lecture 4: Set Up CNN With Keras

Lecture 5: More About CNN With Keras

Lecture 6: Implement Keras CNN On Real Images

Lecture 7: Some More Explanations

Lecture 8: Improve CNN Performance

Lecture 9: CNN For Multiclass Classification

Chapter 8: Working With Textual Data

Lecture 1: Basic Pre-Processing of Text Data

Lecture 2: Detect Frauds Using Keras Autoencoders on Text Data

Lecture 3: Word Embeddings For Classifying Fraud

Lecture 4: Word Embeddings For Classifying Fraud-GloVe

Chapter 9: Recurrent Neural Networks (RNN)

Lecture 1: Some theoretical foundations

Lecture 2: Use RNNs for Text Classification

Lecture 3: Use RNNs for Temporal Data